© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55669
    Prev
    Next
    INDEX
    Explanations

    Here is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enga
    -0.08
    etti
    -0.08
    oura
    -0.07
    èĢ¦
    -0.07
    esis
    -0.07
    оÑĢ
    -0.07
    schw
    -0.07
    å°±éĢģ
    -0.06
    æĽ´è¿ľ
    -0.06
    egro
    -0.06
    POSITIVE LOGITS
    ®
    0.07
    æľĢæĸ°ç«łèĬĤ
    0.07
    è¹ĭ
    0.07
    å¸Īé£İ
    0.07
    -syntax
    0.07
     *__
    0.07
    inded
    0.07
    à¸ĭะ
    0.07
    heb
    0.07
    %!
    0.07
    Activations Density 0.052%

    No Known Activations